Gemini 4 Argon

POST/v1/chat/completions

Gemini 4 Argon is Google's frontier reasoning model announced on September 30, 2026; it is not yet generally available on SandBase, and specifications and pricing will be confirmed at launch. Google built it to sustain deep reasoning across long-horizon work in software engineering, enterprise knowledge work such as legal and finance, and cybersecurity defense, and announced an output token limit of up to 1M tokens. It is currently rolling out only to trusted cyber defenders and testers, with developer API access to follow.

Request body

Parameters supported by this model. Values, defaults, and limits are read from the model registry.

stringmodelrequired

Model identifier. Set to google/gemini-4-argon.

Default: google/gemini-4-argon

array<object>messagesrequired

Conversation messages in system, user, or assistant order.

Optional<integer>max_tokens

Maximum number of tokens the model may generate in the response.

Maximum: 1048576

Optional<number>temperature

Sampling temperature. Lower values are more deterministic; higher values are more creative.

Range: 0 to 2

Default: 1

Optional<number>top_p

Nucleus sampling threshold. Use this or temperature, but usually not both.

Range: 0 to 1

Optional<boolean>stream

When true, returns incremental Server-Sent Events instead of one completed response.

Default: false

Optional<array>tools

Tool definitions that the model may call during the response.

Optional<string>tool_choice

Controls whether the model may call a tool and, when supported, which tool it must call.

Optional<object>response_format

Controls the response format, including JSON mode or structured JSON output when supported.

Optional<array<string>>stop

Sequences that stop generation when the model produces one of them.

Optional<integer>seed

Seed used to make sampling more reproducible when the provider supports it.

Response Schema

Fields returned by this model API response.

array<object>choicesrequired

Generated completion choices.

stringidrequired

Unique chat completion identifier.

stringmodelrequired

Model that generated the response.

Optional<object>usage

Token usage when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: chat, vision, reasoning, coming-soon

stringexecution_moderequired

Execution mode declared by the model registry.

Default: sync

curl -X POST https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Describe this product in one sentence."
    }
  ]
}'

Response200 OK

{
  "id": "chatcmpl_abc123",
  "model": "google/gemini-4-argon",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "A concise product description."
      }
    }
  ]
}